Morphological Segmentation with Neural Networks: Performance Effects of Architecture, Data Size, and Cross-Lingual Transfer in Seven Languages
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A10511638" target="_blank" >RIV/00216208:11320/25:10511638 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Morphological Segmentation with Neural Networks: Performance Effects of Architecture, Data Size, and Cross-Lingual Transfer in Seven Languages
Original language description
We present a comparison of neural network-based morphological segmenters trained on morphologically segmented datasets from seven European languages: Czech, English, French, German, Italian, Dutch, and Slovak. Our aim is to investigate how different model architectures and dataset sizes influence segmentation quality, and how performance varies across languages. To this end, we evaluate recurrent and convolutional neural network models and compare them to widely used unsupervised baseline methods. In selecting the datasets, we prioritized linguistic accuracy and segmentation completeness. We also explore the impact of cross-lingual transfer learning on model performance. Our results show that neural models trained on as few as 125 words outperform unsupervised methods. Moreover, for closely related languages, zero-shot cross-lingual transfer learning can also surpass unsupervised baselines. Overall, we observe consistent performance patterns across languages.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
28th International Conference on Text, Speech and Dialogue (Part II)
ISBN
978-3-032-02551-7
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
275-286
Publisher name
Springer
Place of publication
Cham, Switzerland
Event location
Erlangen, Germany
Event date
Aug 25, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—